An MCP server for care-centered AI safety evaluation that scores text, detects threats and jailbreak attempts, analyzes relationship health and burnout risk, and evaluates responses against the Care Membrane framework. It can be used as a pre-action validation gate to allow, escalate, or block agent actions.
From the registry: Care Membrane MCP Server by MEOK AI Labs
$ pip install mcp$ git clone https://github.com/CSOAI-ORG/care-membrane-mcp.githttps://github.com/CSOAI-ORG/care-membrane-mcpPlease install the `care-membrane-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Python MCP package dependency** — The README's quick start installs the MCP Python package before running the server. Run: `pip install mcp`
- **Obtain the server code** — The README instructs cloning the repository locally before running server.py. Run: `git clone https://github.com/CSOAI-ORG/care-membrane-mcp.git` (https://github.com/CSOAI-ORG/care-membrane-mcp)
Canonical MCP server config (stdio transport):
- command: `python`
- args: ["server.py"]
Note: The README provides a local stdio setup only: run python server.py from the cloned repository directory. It also mentions pip install care-membrane-mcp in an example, but does not document an executable entrypoint or MCP config shape for the PyPI package, so the documented repo-based launch is the usable canonical config.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.